Taboo searching method used for electrocardial characteristic selection

A tabu search algorithm and tabu search technology, applied in the field of physiological signal emotion recognition, can solve problems such as non-optimal results, feature selection not covering, dimension disaster, etc.

Inactive Publication Date: 2013-11-13
SOUTHWEST UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In feature selection, using the traditional tabu search algorithm often leads to the curse of dimensionality, resulting in feature selection not being able to cover all possible solutions, so that the final result of feature selection is not the optimal solution.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Taboo searching method used for electrocardial characteristic selection
  • Taboo searching method used for electrocardial characteristic selection
  • Taboo searching method used for electrocardial characteristic selection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be further elaborated below in conjunction with the accompanying drawings and specific embodiments.

[0028] A feature selection method for emotion recognition based on electrocardiographic signals, comprising the following steps:

[0029] 1. Emotional ECG data collection process;

[0030] The experimental equipment adopts polychannel physiological recorder MP150 provided by American Biopac Company. The subjects of the experiment were 391 first-year undergraduate students aged 17-20. All the subjects who made an appointment to participate in this experiment voluntarily were in good health and had no history of heart disease or mental disease. The experimental materials are fragments selected from a large number of movies that have good eliciting effects on the six emotions of happiness, surprise, disgust, sadness, anger, and fear. Before the experiment, the main experimenter asked the subjects to fill in personal information, a consent form ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a taboo searching method used for electrocardial characteristic selection, comprising the following steps: forming a two-dimensional table L of (N-1) rows and N columns by using a sequential backward algorithm, wherein N is the total dimension numbers of selected characteristics, each column represents one characteristic, each row is called as one space, n characteristics are selected in the nth space and n is not more than (N-1) and not less than 1; representing the value of each element in the table by '0' or '1', wherein '0' represents that the element is not selected during characteristic selection, and '1' represents that the element is selected; solving the selected characteristic in each space by using a taboo searching algorithm to obtain a table S formed by the solution of each space; and selecting the solution with the maximum fitness function in each space as a final characteristic selection result. In the taboo searching method, a selection process is completed in combination with a Fisher classifier by using a space-partitioning method, and the defect of local optimum in the basic taboo searching algorithm is overcome.

Description

technical field [0001] The invention relates to a physiological signal emotion recognition method, in particular to an electrocardiographic feature selection method. Background technique [0002] Emotion recognition is an important part of the field of affective computing. If you want computers to recognize human emotions from faces, gestures, voice and physiological signals, you must first allow computers to recognize emotions, so emotion recognition is very important. Emotion recognition mainly includes body emotion recognition, facial expression emotion recognition, voice emotion recognition and physiological signal emotion recognition. In the article "Application of Heart Rate Variability in Psychosomatic Diseases and Emotional Disorders (Advances in Psychology, 2006, 14(2): 261-265)", it is proposed that the emotional state revealed by facial expressions, language postures, etc. System control, easy to be controlled by subjective consciousness. The physiological signa...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): A61B5/0402A61B5/0452G06F17/30
Inventor 刘光远邱红
Owner SOUTHWEST UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap